searxng

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the platform's execution tools to run its local Python logic script via the uv package manager.
  • [DATA_EXFILTRATION]: The implementation performs network requests to an external URL provided via environment variables. It explicitly disables SSL certificate verification and suppresses security warnings, which creates a vulnerability to man-in-the-middle attacks during data retrieval.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through ingested search data. Ingestion points: Search results from the SearXNG API are pulled into the agent context in scripts/searxng.py. Boundary markers: No delimiters are used to protect the agent from instructions embedded in result snippets. Capability inventory: The script's capabilities are limited to networking and console output, reducing the impact of potential injections. Sanitization: The script truncates search snippets but does not filter for injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 11:32 PM
Security Audit — agent-trust-hub — searxng